NotFittedError:TfidfVectorizer - 没有安装词汇表

Question

我正在尝试使用scikit-learn/pandas构建一个情绪分析器.构建和评估模型有效,但尝试对新样本文本进行分类则不然.

我的代码:

import csv
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import BernoulliNB
from sklearn.metrics import classification_report
from sklearn.metrics import accuracy_score

infile = 'Sentiment_Analysis_Dataset.csv'
data = "SentimentText"
labels = "Sentiment"


class Classifier():
    def __init__(self):
        self.train_set, self.test_set = self.load_data()
        self.counts, self.test_counts = self.vectorize()
        self.classifier = self.train_model()

    def load_data(self):

        df = pd.read_csv(infile, header=0, error_bad_lines=False)
        train_set, test_set = train_test_split(df, test_size=.3)
        return train_set, test_set

    def train_model(self):
        classifier = BernoulliNB()
        targets = self.train_set[labels]
        classifier.fit(self.counts, targets)
        return classifier


    def vectorize(self):

        vectorizer = TfidfVectorizer(min_df=5,
                                 max_df = 0.8,
                                 sublinear_tf=True,
                                 ngram_range = (1,2),
                                 use_idf=True)
        counts = vectorizer.fit_transform(self.train_set[data])
        test_counts = vectorizer.transform(self.test_set[data])

        return counts, test_counts

    def evaluate(self):
        test_counts,test_set = self.test_counts, self.test_set
        predictions = self.classifier.predict(test_counts)
        print (classification_report(test_set[labels], predictions))
        print ("The accuracy score is {:.2%}".format(accuracy_score(test_set[labels], predictions)))


    def classify(self, input):
        input_text = input

        input_vectorizer = TfidfVectorizer(min_df=5,
                                 max_df = 0.8,
                                 sublinear_tf=True,
                                 ngram_range = (1,2),
                                 use_idf=True)
        input_counts = input_vectorizer.transform(input_text)
        predictions = self.classifier.predict(input_counts)
        print(predictions)

myModel = Classifier()

text = ['I like this I feel good about it', 'give me 5 dollars']

myModel.classify(text)
myModel.evaluate()

错误:

Traceback (most recent call last):
  File "sentiment.py", line 74, in <module>
    myModel.classify(text)
  File "sentiment.py", line 66, in classify
    input_counts = input_vectorizer.transform(input_text)
  File "/home/rachel/Sentiment/ENV/lib/python3.5/site-packages/sklearn/feature_extraction/text.py", line 1380, in transform
    X = super(TfidfVectorizer, self).transform(raw_documents)
  File "/home/rachel/Sentiment/ENV/lib/python3.5/site-packages/sklearn/feature_extraction/text.py", line 890, in transform
    self._check_vocabulary()
  File "/home/rachel/Sentiment/ENV/lib/python3.5/site-packages/sklearn/feature_extraction/text.py", line 278, in _check_vocabulary
    check_is_fitted(self, 'vocabulary_', msg=msg),
  File "/home/rachel/Sentiment/ENV/lib/python3.5/site-packages/sklearn/utils/validation.py", line 690, in check_is_fitted
    raise _NotFittedError(msg % {'name': type(estimator).__name__})
sklearn.exceptions.NotFittedError: TfidfVectorizer - Vocabulary wasn't fitted.

我不确定问题是什么.在我的分类方法中,我创建了一个全新的矢量化器来处理我想要分类的文本,与用于从模型创建训练和测试数据的矢量化器分开.

谢谢

Answer 1

你已经安装了一个矢量化器,但你把它扔掉了,因为它在你的vectorize函数的生命周期中不存在.相反,在模型vectorize转换后保存它:

self._vectorizer = vectorizer

然后在你的classify函数中,不要创建一个新的矢量化器.相反,使用您在训练数据中拟合的那个:

input_counts = self._vectorizer.transform(input_text)

Answer 2

另存vectorizer为pickle或joblib文件并在您想要预测时加载它。

pickle.dump(vectorizer, open("vectorizer.pickle", "wb")) //Save vectorizer
pickle.load(open("models/vectorizer.pickle", 'rb'))     // Load vectorizer

Answer 3

您可以同时保存模型和矢量化器，稍后也可以使用它们：我是这样做的：

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.svm import LinearSVC
import pickle


# Train the classification model
def train_model():
    df = pd.read_json('intent_data.json')

    X_train, X_test, y_train, y_test = train_test_split(df['Utterance'], df['Intent'], random_state=0)

    count_vect = CountVectorizer()
    X_train_counts = count_vect.fit_transform(X_train)
    tfidf_transformer = TfidfTransformer()
    X_train_tfidf = tfidf_transformer.fit_transform(X_train_counts)

    model = LinearSVC().fit(X_train_tfidf, y_train)

    # Save the vectorizer
    vec_file = 'vectorizer.pickle'
    pickle.dump(count_vect, open(vec_file, 'wb'))

    # Save the model
    mod_file = 'classification.model'
    pickle.dump(model, open(mod_file, 'wb'))


# Load the classification model from disk and use for predictions
def classify_utterance(utt):
    # load the vectorizer
    loaded_vectorizer = pickle.load(open('vectorizer.pickle', 'rb'))

    # load the model
    loaded_model = pickle.load(open('classification.model', 'rb'))

    # make a prediction
    print(loaded_model.predict(loaded_vectorizer.transform([utt])))